KLASIFIKASI DAN ANALISIS SENTIMEN PADA DATATWITTER MENGGUNAKAN ALGORTIMA NAÏVE BAYES(STUDI KASUS: PEKAN OLAHRAGA NASIONAL XX 2021)

• Main Author: Krisna Jonathan Sitorus, (Author)
• Format: Book
• Published: 2022-07-20.
• Subjects: Thesis; NonPeerReviewed
• Online Access: Link Metadata
• Notes: http://repository.upnvj.ac.id/19780/1/ABSTRAK.pdf; http://repository.upnvj.ac.id/19780/13/AWAL.pdf; http://repository.upnvj.ac.id/19780/3/BAB%20I.pdf; http://repository.upnvj.ac.id/19780/4/BAB%20II.pdf; http://repository.upnvj.ac.id/19780/5/BAB%20III.pdf; http://repository.upnvj.ac.id/19780/6/BAB%20IV.pdf; http://repository.upnvj.ac.id/19780/7/BAB%20V.pdf; http://repository.upnvj.ac.id/19780/8/DAFTAR%20PUSTAKA.pdf; http://repository.upnvj.ac.id/19780/9/RIWAYAT%20HIDUP.pdf; http://repository.upnvj.ac.id/19780/10/LAMPIRAN.pdf; http://repository.upnvj.ac.id/19780/11/HASIL%20PLAGIARISME.pdf; http://repository.upnvj.ac.id/19780/12/ARTIKEL%20KI.pdf
• Keywords: Q Science (General); T Technology (General)

The world of technology is currently developing very rapidly, people can now freely access and express themselves using social media as an example, namely Twitter. Many Twitter users express their opinions through the tweets they send on social media, especially regarding the XX 2021 National Sports Week (PON) ago. Several types of tweets that are appreciative of the event are often seen, but not infrequently there are also tweets that are complaining about the implementation of the XX PON. From this problem, a research was conducted on sentiment analysis on twitter data regarding PON XX using the Naïve Bayes method. The amount of data that is crawled is 1000 data and then the data goes through a duplicate data removal process so that it produces 218 tweets and has not been labeled. Before the process of classifying the data obtained, the data must be labeled and cleaned first before entering the text processing stage, then the data is given a weight for each word with a Term Frequency-Inverse Document Frequency (TF-IDF) which will be used in the future.as a feature. Then, because the data with positive and negative labels have significantly different amounts, the Synthetic Minority Oversampling Technique (SMOTE) method was used to balance the data. The next stage is the distribution of data by 80% 20% and classified by the Naive Bayes method. The results obtained from this study are obtained that the test data get 99% accuracy, 100% precision, 98% recall.